V.Gripon, X.Jiang, C.Berrou, Non binary alphabet Willshaw networks. To be submitted to Neuro-computing.


H. Jarollahi, N. Onizawa, V. Gripon, T. Hanyu and W. J. Gross, "Algorithm and Architecture for a Multiple-Field Context-Driven Search Engine Using Fully-Parallel Clustered Associative Memories," in Proceedings of SiPS, October 2014. To appear.


V. Gripon, V. Skachek and M. Rabbat, "Sparse Binary Matrices as Efficient Associative Memories," in Proceedings of the 52nd Allerton conference, October 2014. In press.


Mheich, A., Hassan, M., Dufor, O., Khalil, M., Berrou, C., & Wendling, F.  (2014, September). Spatiotemporal analysis of brain functional connectivity. In Medical & Biological Engineering & Computing (MBEC), 2014 6th European Conference of the International Federation for Medical and Biological Engineering. IEEE. Submitted to. 


H. Jarollahi, N. Onizawa, V. Gripon, N. Sakimura, T. Sugibayashi, T. Endoh, H. Ohno, T. Hanyu and W. J. Gross, "A Non-Volatile Associative Memory-Based Context-Driven Search Engine Using 90 nm CMOS MTJ-Hybrid Logic-in-Memory Architecture," in Journal on Emerging and Selected Topics in Circuits and Systems, 2014. In press.


B. Boguslawski, V. Gripon, F. Seguin and F. Heitzmann, "Twin Neurons for Efficient Real-World Data Distribution in Networks of Neural Cliques. Applications in Power Management in Electronic circuits," in IEEE Transactions on Neural Networks and Learning Systems, August 2014. Submitted to.


C. Berrou, O. Dufor, V. Gripon and X. Jiang, “Information, noise, coding, modulation: what about the brain”, 8th Int’l Symposium on Turbo Codes & Iterative Information Processing, Bremen, Germany, Aug. 2014.

    Abstract— At the microscopic level, the brain is fundamentally a matter of physics and chemistry, as all the components of the universe are. At the macroscopic scale, behavior, psychology and affects are the main dimensions of its life. To convert atoms and molecules into intelligence, some kind of information has to be fixed in the grey matter of the cerebral cortex. The way this "mental information" is materialized and processed is still an enigma, probably the most puzzling problem addressed to science nowadays. At this mesoscopic level of the brain functioning, the concepts to consider are likely the same as those considered in communication and information theory, mainly information, noise, coding and modulation. This paper proposes some ideas that could help understand some features of the brain in an information-processing perspective.


M. Hassan, O. Dufor, I. Merlet, C. Berrou and F. Wendling, "EEG source connectivity analysis: from dense array recordings to brain networks," PLoS ONE, 9(8): e105041, Aug. 2014.

    Abstract—The recent past years have seen a noticeable increase of interest for electroencephalography (EEG) to analyze functional connectivity through brain sources reconstructed from scalp signals. Although considerable advances have been done both on the recording and analysis of EEG signals, a number of methodological questions are still open regarding the optimal way to process the data in order to identify brain networks. In this paper, we analyze the impact of three factors that intervene in this processing: i) the number of scalp electrodes, ii) the combination between the algorithm used to solve the EEG inverse problem and the algorithm used to measure the functional connectivity and iii) the frequency bands retained to estimate the functional connectivity among neocortical sources. Using High-Resolution (hr) EEG recordings in healthy volunteers, we evaluated these factors on evoked responses during picture recognition and naming task. The main reason for selection this task is that a solid literature background is available about involved brain networks (ground truth). From this a priori information, we propose a performance criterion based on the number of connections identified in the regions of interest (ROI) that belong to potentially activated networks. Our results show that the three studied factors have a dramatic impact on the final result (the identified network in the source space) as strong discrepancies were evidenced depending on the methods used. They also suggest that the combination of weighted Minimum Norm Estimator (wMNE) and the Phase Synchronization (PS) methods applied on High-Resolution EEG in beta/gamma bands provides the best performance in term of topological distance between the identified network and the expected network in the above-mentioned cognitive task.


DH Kim-Dufor, P.Tigreat, "Minimum amount of information necessary for written word recognition". 2014 Korean Society for Language and Information Workshop on Meaning and Cognition, Seoul National University, Seoul, Korea  


Bartosz Boguslawski, Vincent Gripon, Fabrice Seguin and Frédéric Heitzmann, "Huffman Coding for Storing Non-uniformly Distributed Messages in Networks of Neural Cliques" in Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, July 2014. To appear.


X. Jiang, V. Gripon, C. Berrou and M. Rabbat, "Storing sequences in binary tournament-based neural networks," submitted to IEEE Trans. Neural Networks and Learning Systems, July 2014. Submitted to.

    Abstract—An extension to a recently introduced architecture of clique-based neural networks is presented. This extension makes it possible to store sequences with high efficiency. To obtain this property, network connections are provided with orientation and with flexible redundancy carried by both spatial and temporal redundancy, a mechanism of anticipation being introduced in the model. In addition to the sequence storage with high efficiency, this new scheme also offers biological plausibility. In order to achieve accurate sequence retrieval, a double layered structure combining hetero-association and auto-association is also proposed.

Z. Yao, V. Gripon and M. Rabbat, "A GPU-based Associative Memory using Sparse Neural Networks," in Proceedings of the PCNN-14 conference, July 2014.


DH Kim-Dufor, P.Tigreat, "Quantité d’information minimale pour la reconnaissance de mots écrits". GLAT 2014, Télécom Bretagne, Brest, France


B. Kamary Aliabadi, C. Berrou, V. Gripon and X. Jiang, "Storing sparse messages in networks of neural cliques," IEEE Trans. Neural Networks and Learning Systems, vol. 25, n° 5, pp. 980-989, May 2014. [Manuscript].

    Abstract—An extension to a recently introduced binary neural network is proposed to allow the storage of sparse messages, in large numbers and with high memory efficiency. This new network is justified both in biological and informational terms. The storage and retrieval rules are detailed and illustrated by various simulation results.

F. Leduc-Primeau, V. Gripon, M. Rabbat and W. Gross, "Cluster-based Associative Memories Built From Unreliable Storage," in ICASSP, pp. 8370--8374, May 2014.


M. Rabbat and V. Gripon, "Towards a Spectral Characterization of Signals Supported on Small-World Networks," in ICASSP, pp. 4793--4797, May 2014.


A. Aboudib, V. Gripon and X. Jiang, "A study of retrieval algorithms of sparse messages in networks of neural cliques," in Proceedings of Cognitive 2014, May 2014. To appear.






Z. Yao, V. Gripon and M. G. Rabbat, "A Massively Parallel Associative Memory Based on Sparse Neural Networks," in Transactions on Parallel and Distributed Systems, December 2013. Submitted to. [Manuscript].


H. Jarollahi, V. Gripon, N. Onizawa and W. J. Gross, "Algorithm andArchitecture for a Low-Power Content-Addressable Memory Based onSparse-Clustered Networks," in Transactions on Very Large Scale Integration Systems, October 2013. In Press.


V. Gripon, V. Skachek and M. Rabbat, “Sparse structured associative memories as efficient set-membership data structures”, in Proceedings of the 51th Annual Allerton Conference on Communication, Control and Computing, Monticello, Illinois, pp. 500--505, Oct. 2013 


H. Jarollahi, N. Onizawa, V. Gripon and W. J. Gross, "Algorithm and Architecture of Fully-Parallel Associative Memories Based on Sparse Clustered Networks," in Journal of Signal Processing Systems, pp. 1--13, 2014.


V. Gripon and M. Rabbat, "Maximum Likelihood Associative Memories," in Proceedings of Information Theory Workshop, pp.1--5, September 2013. To appear. [Manuscript].


V. Gripon and X. Jiang “Mémoires associatives pour observations floues” in Proceedings of XXIV-th Gretsi seminar, Sept. 2013.


M. Hassan, O. Dufor, A. Mheich, C. Berrou and F. Wendling, “Graph-based analysis of brain connectivity during spelling task”, 2nd IEEE Int’l Conference on Advances in Biomedical Engineering, Tripoli, Lebanon, Sept. 2013.


V. Gripon and M. Rabbat, “Maximum likelihood associative memories”, IEEE Information Theory Workshop, Seville, Spain, Sept. 2013.


V. Gripon and M. Rabbat, “Reconstructing a graph from path traces”, IEEE Int’l Symposium on Information Theory, Istanbul, Turkey, July 2013. To appear. [Manuscript]


Benoit Larras, Bartosz Boguslawski, Cyril Lahuec, Matthieu Arzel, Fabrice Seguin, Frédéric Heitzmann, "Analog Encoded Neural Network for Power Management in MPSoC" in Proceedings of the 11th IEEE International NEWCAS Conference, June 2013.


B. Larras, B. Boguslawski, C. Lahuec, M. Arzel, F. Seguin and F. Heitzmann, “Analog encoded neural network for power management in MPSoC”, IEEE Int’l NEWCAS Conference, Paris, France, June 2013.


Benoit Larras, Cyril Lahuec, Matthieu Arzel and Fabrice Seguin, "An analog circuit for encoded neural networks," in Proceedings of 2013 IEEE International Symposium on Circuits and Systems, May 2013.


B. Larras, C. Lahuec, M. Arzel and F. Seguin, “Analog implementation of encoded neural networks”, IEEE International Symposium on Circuits and Systems, pp. 1-4, Beijing, China, May 2013.


H. Jarollahi, V. Gripon, N. Onizawa and W. J. Gross, "A Low-Power Content-Adressable-Memory Based on Clustered-Sparse-Networks," in Proceedings of 24th International Conference on Application-specific Systems, Architectures and Processors, June 2013. To appear. [Manuscript].


H. Jarollahi, N. Onizawa, V. Gripon and W. J. Gross, “Reduced-complexity binary-weight-coded associative memories”, ICASSP 2013, Vancouver, Canada, May 2013. [Manuscript]





[LIVRE] Claude Berrou and Vincent Gripon. "Petite mathématique du cerveau: Une théorie de l'information mentale." Odile Jacob, 2012.

    Abstract About the neuron, the fundamental component of the brain, we know almost everything. Of the mental information it processes, we know almost nothing. In what "material" form and according to which internal organization does our brain store familiar faces, favorite poems and phone numbers? In what way does it recall them on demand? These questions which have to do with mental information come under information theory, originally formulated by specialists in telecommunications and coding rather than under biology and neuroanatomy.                                                                                                                          
    This very accessible book brings a first concrete, mathematically coherent and biologically plausible answer on the way the neural network sets and recalls its knowledge components. In an original theory get involved neurons and graphs, error correcting codes and cortical columns, neural "cliques" and other "tournaments", in search of the algorithms of our brain. The prospects of development offered by this theory and the entirely digital model of cerebral memory it leads to are numerous and promising in neurosciences as well as in the field of artificial intelligence.


V. Gripon, M. Rabbat, V. Skachek and W. J. Gross, “Compressing multisets using tries”, IEEE Information Theory Workshop, pp. 647-651, Lausanne, Switzerland, Sept. 2012. [Manuscript]. [Presentation]


V. Gripon, V. Skachek, W. J. Gross and M. Rabbat, “Random clique codes”, in Proceedings of 7th Int’l Symposium on Turbo Codes & Iterative Information Processing, pp. 121-125, Gothenburg, Sweden, Aug. 2012. [Manuscript]. [Presentation]


X. Jiang, V. Gripon and C. Berrou, “Learning long sequences in binary neural networks”, Cognitive 2012, pp. 165-170, Nice, France, July 2012. [Manuscript]


H. Jarollahi, N. Onizawa, V. Gripon and W. J. Gross, “Architecture and implementation of an associative memory using sparse clustered networks”, IEEE Int’l Symposium on Circuits and Systems, pp. 2901-2904, Seoul, Korea, May 2012. [Manuscript]. [Presentation]


V. Gripon and C. Berrou, “Nearly-optimal associative memories based on constant weight codes”, ITA workshop, San Diego, USA, pp. 269-273, Feb. 2012. [Manuscript]. [Presentation]




V. Gripon and C. Berrou, "Sparse neural networks with large learning diversity," in IEEE Transactions on Neural Networks, Volume 22, Number 7, pp. 1087--1096, july 2011. [Manuscript].


V. Gripon and C. Berrou, "A simple and efficient way to store many messages using neural cliques," in Proceedings of IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, Paris, France, pp. 54--58, April 2011. [Manuscript]. [Presentation]

Télécom Bretagne
  • Hosted by Telecom Bretagne

  • Technopole Brest-Iroise - CS 83818 - 29238 Brest Cedex 3 - France - Tel : 33 (0)2 29 00 11 11 - Fax : 33 (0)2 29 00 10 00